Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7736
    Prev
    Next
    INDEX
    Explanations

    instances of organizations and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.09
    3:0.11
    4:0.15
    5:0.11
    6:0.04
    7:0.13
    8:0.05
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
     wards
    -2.27
     corro
    -2.16
     antid
    -2.10
     corros
    -2.06
    ither
    -1.94
     weakening
    -1.94
     cumbers
    -1.91
    rongh
    -1.90
     ILCS
    -1.89
    olesc
    -1.88
    POSITIVE LOGITS
    Interview
    3.34
     Interview
    2.67
     listener
    2.66
     Highlights
    2.58
    Talking
    2.50
     Talking
    2.49
     Talk
    2.44
     Talks
    2.43
     Topics
    2.38
    VICE
    2.29
    Activations Density 0.488%

    No Known Activations